Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 451 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.6940. Min Act: -0.1699

Data Index: 868480 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.6628. Min Act: -0.1700

Data Index: 222477 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.6003. Min Act: -0.1684

Data Index: 1350884 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.6003. Min Act: -0.1699

Data Index: 715160 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.6003. Min Act: -0.1699

Data Index: 3917 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.6315. Min Act: -0.1696

Data Index: 656850 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.5378. Min Act: -0.1699

Data Index: 297799 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.6003. Min Act: -0.1700

Data Index: 61385 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.5378. Min Act: -0.1699

Data Index: 374059 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.5690. Min Act: -0.1700

Data Index: 79158 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.5690. Min Act: -0.1700

Data Index: 209037 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.5378. Min Act: -0.1700

Data Index: 307311 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.5378. Min Act: -0.1700

Data Index: 290915 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.5378. Min Act: -0.1700

Data Index: 681252 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.4753. Min Act: -0.1700

Data Index: 127434 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.4753. Min Act: -0.1699

Data Index: 516499 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.5690. Min Act: -0.1700

Data Index: 99480 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.5065. Min Act: -0.1698

Data Index: 605759 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.4753. Min Act: -0.1700

Data Index: 739894 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 5.6940. Min Range: -5.6940

Max Act: 5.4440. Min Act: -0.1700

Data Index: 585078 (C4 (Web Text))

Max Activating Token Index: 911